Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49124
    Prev
    Next
    INDEX
    Explanations

    qualified

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mish
    -0.08
     injunction
    -0.08
     Kek
    -0.08
     stylesheet
    -0.08
     cliff
    -0.08
     karya
    -0.08
     strerror
    -0.08
     临
    -0.08
    =file
    -0.07
     संरक्षण
    -0.07
    POSITIVE LOGITS
    .ready
    0.10
     prospects
    0.09
    _ready
    0.09
    ready
    0.09
    (filtered
    0.08
     ready
    0.08
     Ready
    0.08
     готовы
    0.08
     vetted
    0.08
    	filter
    0.08
    Activations Density 0.012%

    No Known Activations